GCHR：用于样本高效强化学习的目标条件后见正则化
GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
AI总结：
本文提出后见目标条件正则化（HGR）与后见自模仿正则化（HSR），通过生成动作正则化先验最大化经验利用率，显著提升了离线策略GCRL在稀疏奖励下的样本效率和性能。
摘要：
具有稀疏奖励的目标条件强化学习（GCRL）仍是强化学习中的一个基本挑战。尽管后见经验回放（HER）通过对已收集轨迹用实现的目标进行重标记展现出潜力，但我们认为，仅靠轨迹重标记并未充分利用离线策略GCRL方法中的可用经验，导致样本效率有限。本文提出后见目标条件正则化（HGR），这是一种基于后见目标生成动作正则化先验的技术。结合后见自模仿正则化（HSR），我们的方法使离线策略RL算法能够最大化经验利用率。与采用HER和自模仿技术的现有GCRL方法相比，我们的后见正则化实现了显著更高效的样本重用和最佳性能，我们在一系列导航与操作任务上对此进行了实证证明。
英文摘要：
Goal-conditioned reinforcement learning (GCRL) with sparse rewards remains a fundamental challenge in reinforcement learning. While hindsight experience replay (HER) has shown promise by relabeling collected trajectories with achieved goals, we argue that trajectory relabeling alone does not fully exploit the available experiences in off-policy GCRL methods, resulting in limited sample efficiency. In this paper, we propose Hindsight Goal-conditioned Regularization (HGR), a technique that generates action regularization priors based on hindsight goals. When combined with hindsight self-imitation regularization (HSR), our approach enables off-policy RL algorithms to maximize experience utilization. Compared to existing GCRL methods that employ HER and self-imitation techniques, our hindsight regularizations achieve substantially more efficient sample reuse and the best performances, which we empirically demonstrate on a suite of navigation and manipulation tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
